اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNoCs in Heterogeneous 3D SoCs: Co-Design of Routing Strategies and Microarchitectures
303
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Heterogeneous 3D System-on-Chips (3D SoCs) are the most promising design paradigm to combine sensing and computing within a single chip. A special characteristic of communication networks in heterogeneous 3D SoCs is the varying latency and throughput in each layer. As shown in this work, this variance drastically degrades the network performance. We contribute a co-design of routing algorithms and router microarchitecture that allows to overcome these performance limitations. We analyze the challenges of heterogeneity: Technology-aware models are proposed for communication and thereby identify layers in which packets are transmitted slower. The communication models are precise for latency and throughput under zero load. The technology model has an area error and a timing error of less than 7.4% for various commercial technologies from 90 to 28nm. Second, we demonstrate how to overcome limitations of heterogeneity by proposing two novel routing algorithms called Z+(XY)Z- and ZXYZ that enhance latency by up to 6.5x compared to conventional dimension order routing. Furthermore, we propose a high vertical-throughput router microarchitecture that is adjusted to the routing algorithms and that fully overcomes the limitations of slower layers. We achieve an increased throughput of 2 to 4x compared to a conventional router. Thereby, the dynamic power of routers is reduced by up to 41.1% and we achieve improved flit latency of up to 2.26x at small total router area costs between 2.1% and 10.4% for realistic technologies and application scenarios.
قيم البحث
اقرأ أيضاً
One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence options: from
accelerators accessing off-chip memory directly, bypassing the cache hierarchy, to accelerators having their own private cache. By running real-size applications on FPGA-based prototypes of many-accelerator multi-core SoCs, we show that the best cache-coherence mode for a given accelerator varies at runtime, depending on the accelerators characteristics, the workload size, and the overall SoC status. Cohmeleon applies reinforcement learning to select the best coherence mode for each accelerator dynamically at runtime, as opposed to statically at design time. It makes these selections adaptively, by continuously observing the system and measuring its performance. Cohmeleon is accelerator-agnostic, architecture-independent, and it requires minimal hardware support. Cohmeleon is also transparent to application programmers and has a negligible software overhead. FPGA-based experiments show that our runtime approach offers, on average, a 38% speedup with a 66% reduction of off-chip memory accesses compared to state-of-the-art design-time approaches. Moreover, it can match runtime solutions that are manually tuned for the target architecture.
Mobile system-on-chips (SoCs) are growing in their complexity and heterogeneity (e.g., Arms Big-Little architecture) to meet the needs of emerging applications, including games and artificial intelligence. This makes it very challenging to optimally
manage the resources (e.g., controlling the number and frequency of different types of cores) at runtime to meet the desired trade-offs among multiple objectives such as performance and energy. This paper proposes a novel information-theoretic framework referred to as PaRMIS to create Pareto-optimal resource management policies for given target applications and design objectives. PaRMIS specifies parametric policies to manage resources and learns statistical models from candidate policy evaluation data in the form of target design objective values. The key idea is to select a candidate policy for evaluation in each iteration guided by statistical models that maximize the information gain about the true Pareto front. Experiments on a commercial heterogeneous SoC show that PaRMIS achieves better Pareto fronts and is easily usable to optimize complex objectives (e.g., performance per Watt) when compared to prior methods.
We introduce ratatoskr, an open-source framework for in-depth power, performance and area (PPA) analysis in NoCs for 3D-integrated and heterogeneous System-on-Chips (SoCs). It covers all layers of abstraction by providing a NoC hardware implementatio
n on RT level, a NoC simulator on cycle-accurate level and an application model on transaction level. By this comprehensive approach, ratatoskr can provide the following specific PPA analyses: Dynamic power of links can be measured within 2.4% accuracy of bit-level simulations while maintaining cycle-accurate simulation speed. Router power is determined from RT level synthesis combined with cycle-accurate simulations. The performance of the whole NoC can be measured both via cycle-accurate and RT level simulations. The performance of individual routers is obtained from RT level including gate-level verification. The NoC area is calculated from RT level. Despite these manifold features, ratatoskr offers easy two-step user interaction: First, a single point-of-entry that allows to set design parameters and second, PPA reports are generated automatically. For both the input and the output, different levels of abstraction can be chosen for high-level rapid network analysis or low-level improvement of architectural details. The synthesize NoC model reduces up to 32% total router power and 3% router area in comparison to a conventional standard router. As a forward-thinking and unique feature not found in other NoC PPA-measurement tools, ratatoskr supports heterogeneous 3D integration that is one of the most promising integration paradigms for upcoming SoCs. Thereby, ratatoskr lies the groundwork to design their communication architectures.
Memories that exploit three-dimensional (3D)-stacking technology, which integrate memory and logic dies in a single stack, are becoming popular. These memories, such as Hybrid Memory Cube (HMC), utilize a network-on-chip (NoC) design for connecting t
heir internal structural organizations. This novel usage of NoC, in addition to aiding processing-in-memory capabilities, enables numerous benefits such as high bandwidth and memory-level parallelism. However, the implications of NoCs on the characteristics of 3D-stacked memories in terms of memory access latency and bandwidth have not been fully explored. This paper addresses this knowledge gap by (i) characterizing an HMC prototype on the AC-510 accelerator board and revealing its access latency behaviors, and (ii) by investigating the implications of such behaviors on system and software designs.
Artificial intelligence (AI) technologies have dramatically advanced in recent years, resulting in revolutionary changes in peoples lives. Empowered by edge computing, AI workloads are migrating from centralized cloud architectures to distributed edg
e systems, introducing a new paradigm called edge AI. While edge AI has the promise of bringing significant increases in autonomy and intelligence into everyday lives through common edge devices, it also raises new challenges, especially for the development of its algorithms and the deployment of its services, which call for novel design methodologies catered to these unique challenges. In this paper, we provide a comprehensive survey of the latest enabling design methodologies that span the entire edge AI development stack. We suggest that the key methodologies for effective edge AI development are single-layer specialization and cross-layer co-design. We discuss representative methodologies in each category in detail, including on-device training methods, specialized software design, dedicated hardware design, benchmarking and design automation, software/hardware co-design, software/compiler co-design, and compiler/hardware co-design. Moreover, we attempt to reveal hidden cross-layer design opportunities that can further boost the solution quality of future edge AI and provide insights into future directions and emerging areas that require increased research focus.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
